Search order and rate determination in attribute-based environments

Abstract

A processor may receive input data. The processor may train based on the received input data, a machine learning model to estimate rate elasticity, attraction value, and a dissimilarity index associated with an object query and at least one object attribute. The processor may generate one or more object bundles. The processor may output the one or more object bundles to the user.

What is claimed is: 
     
         1 . A system for determining search order and rate in an attribute-based environment, the system comprising:
 a memory; and   a processor in communication with the memory, the processor being configured to perform operations comprising:   receiving input data, wherein the input data includes, at least, an object query and object information, wherein the object query is generated by a user, and wherein the object information includes, at least, one leading object and at least one object attribute together with a rate range;   training, based on the received input data, a machine learning model to estimate rate elasticity, attraction value, and a dissimilarity index associated with the object query and the at least one object attribute;   generating one or more object bundles, wherein the one or more object bundles include the one leading object and one or more other object attributes associated with the leading product, and wherein the one or more object attributes include the at least one object attribute; and   outputting the one or more object bundles to the user, wherein the one or more object bundles include respective optimized rates based on the one or more object attributes.   
     
     
         2 . The system of  claim 1 , wherein the processor is further configured to perform operations comprising:
 receiving prior user data, wherein the prior user data includes, at least a unique identifier for a prior user, procurement information that includes time series data associated with the procurement of the leading object together with the one or more object attributes.   
     
     
         3 . The system of  claim 2 , wherein the processor is further configured to perform operations comprising:
 generating, based on the object query and the machine learning model, an attribute rate model, wherein the attribute rate model indicates respective rates for the one or more object attributes.   
     
     
         4 . The system of  claim 3 , wherein the attribute rate model captures dependencies across the one or more object attributes using one or more of rate elasticity, attraction value, and a dissimilarity index, and wherein the processor is further configured to perform operations comprising:
 refining the attribute rate model by utilizing a fixed-point iteration.   
     
     
         5 . The system of  claim 4 , wherein the processor is further configured to perform operations comprising:
 generating, based on the machine learning model and the attribute rate model, one or more procurement predictions, wherein the one or more procurement models are respectively associated with the one or more object bundles.   
     
     
         6 . The system of  claim 5 , wherein the processor is further configured to perform operations comprising:
 prioritizing the one or more object bundles based on a predicted procurement propensity by the user.   
     
     
         7 . The system of  claim 1 , wherein the machine learning model includes a nested logit estimation model. 
     
     
         8 . A computer-implemented method for determining search order and rate in an attribute-based environment, the method comprising:
 receiving input data, wherein the input data includes, at least, an object query and object information, wherein the object query is generated by a user, and wherein the object information includes, at least, one leading object and at least one object attribute together with a rate range;   training, based on the received input data, a machine learning model to estimate rate elasticity, attraction value, and a dissimilarity index associated with the object query and the at least one object attribute;   generating one or more object bundles, wherein the one or more object bundles include the one leading object and one or more other object attributes associated with the leading product, and wherein the one or more object attributes include the at least one object attribute; and   outputting the one or more object bundles to the user, wherein the one or more object bundles include respective optimized rates based on the one or more object attributes.   
     
     
         9 . The computer-implemented method of  claim 8 , further comprising:
 receiving prior user data, wherein the prior user data includes, at least a unique identifier for a prior user, procurement information that includes time series data associated with the procurement of the leading object together with the one or more object attributes.   
     
     
         10 . The computer-implemented method of  claim 9 , further comprising:
 generating, based on the object query and the machine learning model, an attribute rate model, wherein the attribute rate model indicates respective rates for the one or more object attributes.   
     
     
         11 . The computer-implemented method of  claim 10 , wherein the attribute rate model captures dependencies across the one or more object attributes using one or more of rate elasticity, attraction value, and a dissimilarity index, and wherein the method further comprises:
 refining the attribute rate model by utilizing a fixed-point iteration.   
     
     
         12 . The computer-implemented method of  claim 11 , further comprising:
 generating, based on the machine learning model and the attribute rate model, one or more procurement predictions, wherein the one or more procurement models are respectively associated with the one or more object bundles.   
     
     
         13 . The computer-implemented method of  claim 12 , further comprising:
 prioritizing the one or more object bundles based on a predicted procurement propensity by the user.   
     
     
         14 . The computer-implemented method of  claim 8 , wherein the machine learning model includes a nested logit estimation model. 
     
     
         15 . A computer program product for determining search order and rate in an attribute-based environment comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations, the operations comprising:
 receiving input data, wherein the input data includes, at least, an object query and object information, wherein the object query is generated by a user, and wherein the object information includes, at least, one leading object and at least one object attribute together with a rate range;   training, based on the received input data, a machine learning model to estimate rate elasticity, attraction value, and a dissimilarity index associated with the object query and the at least one object attribute;   generating one or more object bundles, wherein the one or more object bundles include the one leading object and one or more other object attributes associated with the leading product, and wherein the one or more object attributes include the at least one object attribute; and   outputting the one or more object bundles to the user, wherein the one or more object bundles include respective optimized rates based on the one or more object attributes.   
     
     
         16 . The computer program product of  claim 15 , wherein the processor is further configured to perform operations comprising:
 receiving prior user data, wherein the prior user data includes, at least a unique identifier for a prior user, procurement information that includes time series data associated with the procurement of the leading object together with the one or more object attributes.   
     
     
         17 . The computer program product of  claim 16 , wherein the processor is further configured to perform operations comprising:
 generating, based on the object query and the machine learning model, an attribute rate model, wherein the attribute rate model indicates respective rates for the one or more object attributes.   
     
     
         18 . The computer program product of  claim 17 , wherein the attribute rate model captures dependencies across the one or more object attributes using one or more of rate elasticities, attraction values, and dissimilarity indices, and wherein the processor is further configured to perform operations comprising:
 refining the attribute rate model by utilizing a fixed-point iteration.   
     
     
         19 . The computer program product of  claim 18 , wherein the processor is further configured to perform operations comprising:
 generating, based on the machine learning model and the attribute rate model, one or more procurement predictions, wherein the one or more procurement models are respectively associated with the one or more object bundles.   
     
     
         20 . The computer program product of  claim 19 , wherein the processor is further configured to perform operations comprising:
 prioritizing the one or more object bundles based on a predicted procurement propensity by the user.